© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 14754
    Prev
    Next
    INDEX
    Explanations

    time-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and related temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SY
    -0.85
    Tele
    -0.76
    Hyp
    -0.72
    Ult
    -0.72
    Bul
    -0.72
    Tor
    -0.71
     SY
    -0.71
    Hyd
    -0.71
    Rocket
    -0.70
    Obs
    -0.70
    POSITIVE LOGITS
     locality
    0.75
     avenue
    0.72
    abase
    0.72
    avement
    0.69
     era
    0.69
     occupation
    0.68
     zone
    0.67
     cavity
    0.66
    iversary
    0.65
    bered
    0.65
    Activations Density 0.616%

    No Known Activations